Book Image

TensorFlow Deep Learning Projects

By : Alexey Grigorev, Rajalingappaa Shanmugamani
Book Image

TensorFlow Deep Learning Projects

By: Alexey Grigorev, Rajalingappaa Shanmugamani

Overview of this book

TensorFlow is one of the most popular frameworks used for machine learning and, more recently, deep learning. It provides a fast and efficient framework for training different kinds of deep learning models, with very high accuracy. This book is your guide to master deep learning with TensorFlow with the help of 10 real-world projects. TensorFlow Deep Learning Projects starts with setting up the right TensorFlow environment for deep learning. You'll learn how to train different types of deep learning models using TensorFlow, including Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, and Generative Adversarial Networks. While doing this, you will build end-to-end deep learning solutions to tackle different real-world problems in image processing, recommendation systems, stock prediction, and building chatbots, to name a few. You will also develop systems that perform machine translation and use reinforcement learning techniques to play games. By the end of this book, you will have mastered all the concepts of deep learning and their implementation with TensorFlow, and will be able to build and train your own deep learning models with TensorFlow confidently.

Related Content you might be interested in

Current Title:

Small book image
TensorFlow Deep Learning Projects
Alexey Grigorev | Rajalingappaa Shanmugamani
Mar, 2018 | 320 pages
Small book image
Deep Learning for Computer Vision
Rajalingappaa Shanmugamani
Jan, 2018 | 310 pages
Small book image
Practical Convolutional Neural Networks
Mohit Sewak | Md Rezaul Karim | Pradeep Pujari
Feb, 2018 | 218 pages
Small book image
Deep Learning with Keras
Sujit Pal | Antonio Gulli
Apr, 2017 | 318 pages
Table of Contents (12 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Recognizing traffic signs using Convnets
Recognizing traffic signs using Convnets
The dataset
The CNN network
Image preprocessing
Train the model and make predictions
Follow-up questions
Summary
2
Annotating Images with Object Detection API
Annotating Images with Object Detection API
The Microsoft common objects in context
The TensorFlow object detection API
Presenting our project plan
Provisioning of the project code
Acknowledgements
Summary
3
Caption Generation for Images
Caption Generation for Images
What is caption generation?
Exploring image captioning datasets
Converting words into embeddings
Image captioning approaches
Implementing a caption generation model
Summary
4
Building GANs for Conditional Image Creation
Building GANs for Conditional Image Creation
Introducing GANs
The project
Putting CGAN to work on some examples
Resorting to Amazon Web Service
Acknowledgements
Summary
5
Stock Price Prediction with LSTM
Stock Price Prediction with LSTM
Input datasets – cosine and stock price
Format the dataset
Using regression to predict the future prices of a stock
Long short-term memory – LSTM 101
Stock price prediction with LSTM
Possible follow - up questions
Summary
6
Create and Train Machine Translation Systems
Create and Train Machine Translation Systems
A walkthrough of the architecture
Preprocessing of the corpora
Training the machine translator
Test and translate
Summary
7
Train and Set up a Chatbot, Able to Discuss Like a Human
Train and Set up a Chatbot, Able to Discuss Like a Human
Introduction to the project
The input corpus
Creating the training dataset
Training the chatbot
Chatbox API
Summary
8
Detecting Duplicate Quora Questions
Detecting Duplicate Quora Questions
Presenting the dataset
Starting with basic feature engineering
Creating fuzzy features
Resorting to TF-IDF and SVD features
Mapping with Word2vec embeddings
Testing machine learning models
Building a TensorFlow model
Processing before deep neural networks
Deep neural networks building blocks
Designing the learning architecture
Summary
9
Building a TensorFlow Recommender System
Building a TensorFlow Recommender System
Recommender systems
Matrix factorization for recommender systems
RNN for recommender systems
Summary
10
Video Games by Reinforcement Learning
Video Games by Reinforcement Learning
The game legacy
The OpenAI version
Installing OpenAI on Linux (Ubuntu 14.04 or 16.04)
Exploring reinforcement learning through deep learning
Starting the project
Acknowledgements
Summary
11
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Exploring reinforcement learning through deep learning

In this project, we are not interested in developing a heuristic (a still valid approach to solving many problems in artificial intelligence) or constructing a working PID. We intend instead to use deep learning to provide an agent with the necessary intelligence to operate a Lunar Lander video game session successfully.

Reinforcement learning theory offers a few frameworks to solve such problems:

  • Value-based learning: This works by figuring out the reward or outcome from being in a certain state. By comparing the reward of different possible states, the action leading to the best state is chosen. Q-learning is an example of this approach.
  • Policy-based learning: Different control policies are evaluated based on the reward from the environment. It is decided upon the policy achieving the best results.
  • Model-based learning...
Previous Section
End of Section 5
Next Section